© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130803
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on instances of function or method calls—i.e. identifiers followed by parentheses.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    closing punctuation followed by method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nästa
    -0.96
    a
    -0.95
    byes
    -0.94
     etc
    -0.94
     second
    -0.94
    one
    -0.94
    ()
    -0.94
    :
    -0.93
    给予
    -0.93
     have
    -0.91
    POSITIVE LOGITS
    ウチ
    1.23
     számára
    1.16
     delgado
    1.14
     composés
    1.14
     nettoyer
    1.13
    喏
    1.13
     rekke
    1.12
    Iš
    1.11
     män
    1.11
    født
    1.10
    Activations Density 0.012%

    No Known Activations